© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2837
    Prev
    Next
    INDEX
    Explanations

    instances and phrases related to avoidance strategies or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Adin
    -0.77
    uid
    -0.77
    urance
    -0.74
     Tycoon
    -0.72
    の魔
    -0.71
    andr
    -0.70
    ️
    -0.68
    王
    -0.68
    ector
    -0.67
     サーティワン
    -0.67
    POSITIVE LOGITS
     looting
    0.91
     hurting
    0.84
     repetition
    0.83
     reckoning
    0.82
     harming
    0.79
     contention
    0.79
     stagnation
    0.78
     harm
    0.76
     acquiring
    0.75
     duplication
    0.75
    Activations Density 0.043%

    No Known Activations